CryoSift : an accessible and automated CNN-driven tool for cryo-EM 2D class selection

2025/11/07 by Jan-Hannes Schäfer, Austin Calza, Keegan Hom +6 · 2 voices
Biochemistry, Genetics and Molecular Biology · Materials Science · Physics and Astronomy · #Advanced Electron Microscopy Techniques and Applications #Advanced X-ray Imaging Techniques #Electron and X-Ray Spectroscopy Techniques

paper · pdf · doi:10.1107/s2053230x25008866

openalex created_date 2025/11/07 · openalex publication_date 2025/11/07 · openalex updated_date 2026/08/01

Abstract

Single-particle cryo-electron microscopy (cryo-EM) has become an essential tool in structural biology. However, automating repetitive tasks remains an ongoing challenge in cryo-EM data-set processing. Here, we present a platform-independent convolutional neural network (CNN) tool for assessing the quality of 2D averages to enable the automatic selection of suitable particles for high-resolution reconstructions, termed CryoSift. We integrate CryoSift into a fully automated processing pipeline using the existing cryosparc-tools library. Our integrated and customizable 2D assessment workflow enables high-throughput processing that accommodates experienced to novice cryo-EM users.

Citations

• UCSF ChimeraX: Structure visualization for researchers, educators, and developers
• Non-uniform refinement: adaptive regularization improves single-particle cryo-EM reconstruction
• New tools for automated cryo-EM single-particle analysis in RELION-4.0
• Magellon – an extensible platform for cryo-EM data visualization, management and processing

Discussions

• CryoSift is now out @actacrystf.iucr.org doi.org/10.1107/S205... Thanks to all involved. Happy processing! [bsky, 13 points, 0 comments]
• CryoSift is a platform-independent convolutional neural network tool for assessing the quality of 2D averages to enable the automatic selection of suitable particles for high-resolution reconstruction [bsky, 6 points, 0 comments]

Related

• DeepPicker: a Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM
• CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders
• New tools for automated cryo-EM single-particle analysis in RELION-4.0
• CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection
• CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy